English

NAND-SPIN-Based Processing-in-MRAM Architecture for Convolutional Neural Network Acceleration

Hardware Architecture 2022-04-22 v1 Emerging Technologies

Abstract

The performance and efficiency of running large-scale datasets on traditional computing systems exhibit critical bottlenecks due to the existing "power wall" and "memory wall" problems. To resolve those problems, processing-in-memory (PIM) architectures are developed to bring computation logic in or near memory to alleviate the bandwidth limitations during data transmission. NAND-like spintronics memory (NAND-SPIN) is one kind of promising magnetoresistive random-access memory (MRAM) with low write energy and high integration density, and it can be employed to perform efficient in-memory computation operations. In this work, we propose a NAND-SPIN-based PIM architecture for efficient convolutional neural network (CNN) acceleration. A straightforward data mapping scheme is exploited to improve the parallelism while reducing data movements. Benefiting from the excellent characteristics of NAND-SPIN and in-memory processing architecture, experimental results show that the proposed approach can achieve \sim2.6×\times speedup and \sim1.4×\times improvement in energy efficiency over state-of-the-art PIM solutions.

Keywords

Cite

@article{arxiv.2204.09989,
  title  = {NAND-SPIN-Based Processing-in-MRAM Architecture for Convolutional Neural Network Acceleration},
  author = {Yinglin Zhao and Jianlei Yang and Bing Li and Xingzhou Cheng and Xucheng Ye and Xueyan Wang and Xiaotao Jia and Zhaohao Wang and Youguang Zhang and Weisheng Zhao},
  journal= {arXiv preprint arXiv:2204.09989},
  year   = {2022}
}

Comments

15 pages, accepted by SCIENCE CHINA Information Sciences (SCIS) 2022

R2 v1 2026-06-24T10:54:27.914Z